sandey/blender
1
0
Fork 0
forked from bartvdbraak/blender
Code Pull Requests Activity
06c051363b
blender/intern/cycles
History
Hristo Gueorguiev 06c051363b Cycles: split kernel_shadow_blocked to AO & DL parts 
Reduces memory allocation for split kernel.

This allows for faster rendering due to bigger global size,
specially when GPU memory is limited.

Perfromance results:

                         R9 290 total render time
                        Before    After   Change
BMW                      4:37      4:34   -1.1 %
Classroom               14:43     14:30   -1.5 %
Fishy Cat               11:20     11:04   -2.4 %
Koro                    12:11     12:04   -1.0 %
Pabellon Barcelona      22:01     20:44   -5.8 %
Pabellon Barcelona(*)   15:32     15:09   -2.5 %

(*) without glossy connected to volume
2017-03-09 17:09:37 +01:00
..
app Cycles: Cleanup, style 2017-01-13 15:24:56 +01:00
blender Cycles: CUDA implementation of split kernel 2017-03-08 01:24:53 -05:00
bvh Fix build error with macOS / clang / c++11. 2017-02-25 03:12:53 +01:00
cmake Fix compilation error when CUDA toolkit is not installed 2016-11-07 14:47:10 +01:00
device Cycles: split kernel_shadow_blocked to AO & DL parts 2017-03-09 17:09:37 +01:00
doc Cycles: relicense GNU GPL source code to Apache version 2.0. 2013-08-18 14:16:15 +00:00
graph Cycles: Don't use guarded vector for statically initialized data 2016-10-24 14:18:22 +02:00
kernel Cycles: split kernel_shadow_blocked to AO & DL parts 2017-03-09 17:09:37 +01:00
render Cycles: Seperate kernel loading time from render time 2017-03-08 01:24:55 -05:00
subd Cycles: Cleanup, style 2016-10-24 12:26:12 +02:00
test Cycles: Cleanup, order of arguments to EXPECT_EQ 2017-02-03 11:35:34 +01:00
util Cycles: Use 1-based line number for #line directives 2017-03-08 12:45:18 +01:00
CMakeLists.txt Cycles: Use fast math without finite optimization 2017-02-13 16:25:35 +01:00